GitHub
GitHub’s official server lets AI read and manage code, issues and pull requests in your account. Use GitHub’s hosted version or run it locally with Docker.
Description from the maker (original English)
Multi-account tool broker for AI agents — CLI and MCP.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"janusmcp": {
"command": "npx",
"args": [
"-y",
"@bayway/janusmcp"
]
}
}
}Run this in your terminal
claude mcp add janusmcp -- npx -y @bayway/janusmcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"janusmcp": {
"command": "npx",
"args": [
"-y",
"@bayway/janusmcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"janusmcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@bayway/janusmcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 8, 2026
The registry name was verified with the GitHub account bayway, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.6.2) reached the registry 41 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: GitHub, Desktop Commander, Cloudflare MCP
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
GitHub’s official server lets AI read and manage code, issues and pull requests in your account. Use GitHub’s hosted version or run it locally with Docker.
MCP server for terminal commands, file operations, and process management
Cloudflare MCP servers
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
One credential broker. Every account. From the CLI or MCP. Multi-account tool access for AI agents, with credentials kept local.
One-click buttons require the npm package to be published. See RELEASING.md .
If you work with more than one company, you use the *same* MCP server (Supabase, GitHub, Slack…) with different identities — a different account, email and token per client. Today most LLM clients hold one account at a time per connector: to switch client you disconnect, reconnect, and redo the OAuth login. Every time.
The MCP protocol has no notion of "account": one session = one identity = one set of credentials. JanusMCP fills that gap.
JanusMCP is a local multi-account tool broker for AI agents. It can be used directly from the CLI or as an MCP server in front of the real upstream servers:
janusmcp tools / schema / call invoke tools on demand, with no bulk tool definitions loaded upfront. ┌─────────────────────────────┐ ┌─ Supabase (Client A)
LLM client ─MCP─▶│ JanusMCP broker │─▶ ├─ Supabase (Client B) (Claude/GPT/ │ active-account · vault · │ ├─ GitHub (Client A) Gemini/…) │ per-session scoping │ └─ … └─────────────────────────────┘
You drive it with three control tools that appear in any client: janus_list_accounts, janus_use_account, janus_whoami.
npm install -g @bayway/janusmcp
janusmcp tools janusmcp schema list_tables janusmcp call list_tables --args '{"schemas":["public"]}' --json --timeout 30s
The CLI discovers schemas only when needed, accepts JSON through --args or stdin, supports explicit accounts/profiles, and provides stable exit codes. See the CLI guide and copyable agent instructions.
npx @bayway/janusmcp serve
janusmcp install claude-desktop
Both modes share the same config, OS-keychain vault, OAuth tokens and persisted active account. Use janusmcp daemon start to keep upstream sessions warm across repeated CLI calls.
Once released, install via your favorite channel (all published automatically on each tag — see RELEASING.md):
npx @bayway/janusmcp serve # npm / MCP mode
brew install bayway/janusmcp/janusmcp # Homebrew (macOS/Linux) scoop install janusmcp # Windows docker run --rm -p 7332:7332 ghcr.io/bayway/janusmcp:latest
…or download a prebuilt binary from Releases.
git clone https://github.com/bayway/janusmcp
cd janusmcp/go make build # produces ./bin/janusmcp cp config.example.json config.json # edit with your accounts ./bin/janusmcp serve # stdio, for Claude Desktop/Code
Two Supabase clients, PATs kept in your OS keychain (never in the config):
./bin/janusmcp vault set supabase_client_a # paste the PAT
./bin/janusmcp vault set supabase_client_b
// config.json
{ "bindingMode": "session", "accounts": [ { "id": "client_a", "service": "supabase", "command": "npx", "args": ["-y", "@supabase/mcp-server-supabase@latest", "--read-only", "--project-ref=REF_A"], "env": { "SUPABASE_ACCESS_TOKEN": "vault:supabase_client_a" } }, { "id": "client_b", "service": "supabase", "command": "npx", "args": ["-y", "@supabase/mcp-server-supabase@latest", "--read-only", "--project-ref=REF_B"], "env": { "SUPABASE_ACCESS_TOKEN": "vault:supabase_client_b" } } ] }
Add it to Claude Desktop:
{ "mcpServers": { "janusmcp": {
"command": "/abs/path/janusmcp/go/bin/janusmcp", "args": ["serve"], "env": { "JANUS_CONFIG": "/abs/path/janusmcp/go/config.json" } } } }
For ChatGPT / Gemini / Cursor / Copilot, run HTTP and point them at the URL:
JANUS_TRANSPORT=http JANUS_HTTP_PORT=7332 ./bin/janusmcp serve
Run janusmcp help for the full reference. The essentials:
| Command | What it does | |||
|---|---|---|---|---|
janusmcp serve | Run the broker (default). Transports via env: `JANUS_TRANSPORT=stdio\ | http\ | both, JANUS_HTTP_HOST, JANUS_HTTP_PORT`. | |
janusmcp tools [selector] | Compact tool list for the active (or given) account/profile. --json for full definitions; optional --timeout. | |||
janusmcp schema | Full JSON definition of one tool. --account disambiguates; optional --timeout. | |||
janusmcp call | Invoke a tool. Supports --account, --args, stdin, stable --json, and optional --timeout. | |||
janusmcp use | Persist the active selector for future CLI commands and new MCP sessions. | |||
| `janusmcp daemon start\ | stop\ | restart\ | status` | Manage the optional loopback-only daemon that reuses upstream sessions. |
janusmcp ui | Open the local control panel — add accounts, log in, set secrets. | |||
janusmcp add [id] | Add an account from a template (janusmcp catalog lists them). | |||
janusmcp catalog | List the built-in account templates. | |||
janusmcp connect | Connect an account; for remote OAuth, opens the browser. | |||
janusmcp status | Show each account's login/secret status (no secret values). | |||
janusmcp vault set / delete | Store / remove a secret in the OS keychain. | |||
janusmcp login | OAuth loopback login; token referenced as oauth: . | |||
janusmcp providers | List built-in OAuth providers. | |||
janusmcp install | Configure an LLM client to launch JanusMCP. | |||
janusmcp uninstall | Remove JanusMCP from an LLM client's config. | |||
janusmcp version · janusmcp help | Version · this reference. |
Supported values for install / uninstall: claude-desktop, claude-code, cursor, vscode, gemini, codex, chatgpt, print. Run janusmcp install list (or uninstall list) to see each target and whether it's already configured.
janusmcp install claude-desktop # one-command setup
janusmcp uninstall claude-desktop # clean removal (restart the client afterwards)
Inside any connected client you also get the control tools janus_list_accounts, janus_use_account, janus_whoami, janus_login, janus_use_profile, and janus_with_account.
A profile groups accounts of the same client across different services. Activating it exposes the tools of *all* its accounts together, and each call is routed to the right upstream:
// config.json
{ "accounts": [ { "id": "supabase_a", "service": "supabase", "transport": "http", "url": "https://mcp.supabase.com/mcp", "auth": "oauth" }, { "id": "github_a", "service": "github", "transport": "http", "url": "https://api.githubcopilot.com/mcp/", "auth": "oauth" } ], "profiles": { "client_a": ["supabase_a", "github_a"] } }
Then in chat: janus_use_profile with { "profile": "client_a" } → Supabase and GitHub tools for Client A are available simultaneously. Colliding tool names across accounts are namespaced ( _ ).
janus_with_account runs a single call on another account without changing the active one — e.g. { "account_id": "client_b", "tool": "list_tables" }. Omit tool to list that account's available tools first.
Loading every MCP tool definition into an LLM context is expensive. In code-execution mode an agent (or you) invokes tools on demand from the shell instead — à la "code execution with MCP" — so the context holds only the results it actually asked for:
janusmcp tools # compact list for the active account/profile
janusmcp tools client_a # ...or any account/profile explicitly janusmcp schema list_tables # full input schema of ONE tool, only when needed janusmcp call list_tables --args '{"schemas":["public"]}' janusmcp call ping --account azienda_b # cross-account without switching echo '{"sql":"select 1"}' | janusmcp call db_query # JSON args via stdin too janusmcp call ping --json --timeout 30s # stable envelope for agents
call prints the tool's text content to stdout and exits non-zero on a tool error, so it composes with pipes and scripts. Selectors resolve exactly like in the broker: the persisted active account by default, or any account id / profile name; a name that collides across a profile's accounts must be disambiguated with --account. Secrets resolve through the same vault/OAuth stack as serve — nothing extra to configure.
This makes JanusMCP a first-class citizen for CLI-driven agents (Claude Code, Codex, Cursor agents, or any agent with shell access): instead of registering it as an MCP server, just tell the agent that janusmcp tools / schema / call exist. Discovery, schemas and invocation happen on demand, credentials stay in the keychain, and multi-account switching works the same as over MCP. Both modes share the config and the persisted active account, so you can mix them freely.
For repeated calls, janusmcp daemon start launches an authenticated loopback-only broker. tools, schema, and call auto-detect it and reuse its upstream sessions; --direct bypasses it and --daemon requires it. Set JANUS_DAEMON=auto|require|off to choose a default policy.
| Multi-account, one endpoint | N identities for the same service, no reconnecting | ||
| Identity scoping | per-call → per-session → global, via `bindingMode: global \ | session \ | locked. Session scope needs a real connection: stdio and legacy HTTP have one; MCP 2026-07-28 removed sessions, so there it is per-call (janus_with_account`) or global |
| **Dual transport*
Only the beginning is shown; read the rest in the repo